Scholar Feed

Long-context / context-window extension

Chain-of-Agents (CoA)

Superseded baseline#47 of 53 most-superseded

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites Chain-of-Agents (CoA) as a baseline.

current multi-agent approaches rely heavily on hand-crafted designs, such as predefined roles, fixed collaboration structures, and task-specific prompts (e.g., a serial communication chain in CoA), that may not generalize across diverse tasks.
— Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.